Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3977 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.3310. Min Act: -0.0000

Data Index: 156116 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2614. Min Act: -0.0000

Data Index: 291020 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2462. Min Act: -0.0000

Data Index: 302531 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1292032 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2095. Min Act: -0.0000

Data Index: 389809 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2072. Min Act: -0.0000

Data Index: 444365 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1193511 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2184. Min Act: -0.0000

Data Index: 242794 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1342491 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1505380 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1888. Min Act: -0.0000

Data Index: 594505 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1345077 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1953. Min Act: -0.0000

Data Index: 882195 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1896. Min Act: -0.0000

Data Index: 825843 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1181923 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1603430 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1829. Min Act: -0.0000

Data Index: 785253 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1868. Min Act: -0.0000

Data Index: 940445 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1892. Min Act: -0.0000

Data Index: 660247 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.1733. Min Act: -0.0000

Data Index: 850527 (C4 (Web Text))

Max Activating Token Index: 169